| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01018351543439058, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000339450514479686, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000339450514479686, | |
| "eval_loss": NaN, | |
| "eval_runtime": 726.2115, | |
| "eval_samples_per_second": 6.833, | |
| "eval_steps_per_second": 3.416, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000678901028959372, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001018351543439058, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001357802057918744, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00169725257239843, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002036703086878116, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002376153601357802, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002715604115837488, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002715604115837488, | |
| "eval_loss": NaN, | |
| "eval_runtime": 718.4223, | |
| "eval_samples_per_second": 6.907, | |
| "eval_steps_per_second": 3.453, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003055054630317174, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00339450514479686, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0037339556592765463, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004073406173756232, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0044128566882359185, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.45503262094184e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004752307202715604, | |
| "grad_norm": 1.5681408643722534, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.4089, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00509175771719529, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005431208231674976, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005431208231674976, | |
| "eval_loss": NaN, | |
| "eval_runtime": 723.4605, | |
| "eval_samples_per_second": 6.859, | |
| "eval_steps_per_second": 3.429, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005770658746154662, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006110109260634348, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006449559775114034, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.782172325201155e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00678901028959372, | |
| "grad_norm": 1.0797548294067383, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1937, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0071284608040734065, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007467911318553093, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007807361833032778, | |
| "grad_norm": 0.9458051323890686, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0582, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008146812347512465, | |
| "grad_norm": 0.5507776737213135, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.0312, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008146812347512465, | |
| "eval_loss": NaN, | |
| "eval_runtime": 723.0782, | |
| "eval_samples_per_second": 6.862, | |
| "eval_steps_per_second": 3.431, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008486262861992151, | |
| "grad_norm": 0.3728681802749634, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0167, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008825713376471837, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.009165163890951521, | |
| "grad_norm": 0.16944009065628052, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.0052, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009504614405431207, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009844064919910894, | |
| "grad_norm": 0.10501183569431305, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0033, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01018351543439058, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 8, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7805294805450752e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |